1. You-Dont-Know-JS
A book series on JavaScript. @YDKJS on Twitter.
https://t.co/8jFxTtBDrm
2.Frontend Dev Bookmarks
This is a manually curated collection of resources for front-end web developers.
https://t.co/xRI4tt3IfC)
3. Free Programming Books
This is a repo with all free programming books that are available.
https://t.co/gZGc06WiQ5
4. JavaScript Algorithms
This is a list with algorithms and data structures implemented in JavaScript with explanations and links to further readings.
https://t.co/x6Iyy3l0DU
5. Front-End Checklist
The perfect Front-End Checklist for modern websites and meticulous developers.
https://t.co/3ni2Zb4cKW
6. HTML5 Boilerplate
A professional front-end template for building fast, robust, and adaptable web apps or sites.
https://t.co/9RzsAVh6ZW
7. CSS Pro Tips
A collection of tips to help take your CSS skills pro.
https://t.co/karCNkR0Za
8. Web Fundamentals
Best practices for modern web development.
https://t.co/hxy4bdpjvg
9. Web Gems
A curated list of resources for devs and designers.
https://t.co/MS0olx0CyZ

More from All

How can we use language supervision to learn better visual representations for robotics?

Introducing Voltron: Language-Driven Representation Learning for Robotics!

Paper: https://t.co/gIsRPtSjKz
Models: https://t.co/NOB3cpATYG
Evaluation: https://t.co/aOzQu95J8z

🧵👇(1 / 12)


Videos of humans performing everyday tasks (Something-Something-v2, Ego4D) offer a rich and diverse resource for learning representations for robotic manipulation.

Yet, an underused part of these datasets are the rich, natural language annotations accompanying each video. (2/12)

The Voltron framework offers a simple way to use language supervision to shape representation learning, building off of prior work in representations for robotics like MVP (
https://t.co/Pb0mk9hb4i) and R3M (https://t.co/o2Fkc3fP0e).

The secret is *balance* (3/12)

Starting with a masked autoencoder over frames from these video clips, make a choice:

1) Condition on language and improve our ability to reconstruct the scene.

2) Generate language given the visual representation and improve our ability to describe what's happening. (4/12)

By trading off *conditioning* and *generation* we show that we can learn 1) better representations than prior methods, and 2) explicitly shape the balance of low and high-level features captured.

Why is the ability to shape this balance important? (5/12)

You May Also Like

Oh my Goodness!!!

I might have a panic attack due to excitement!!

Read this thread to the end...I just had an epiphany and my mind is blown. Actually, more than blown. More like OBLITERATED! This is the thing! This is the thing that will blow the entire thing out of the water!


Has this man been concealing his true identity?

Is this man a supposed 'dead' Seal Team Six soldier?

Witness protection to be kept safe until the right moment when all will be revealed?!

Who ELSE is alive that may have faked their death/gone into witness protection?


Were "golden tickets" inside the envelopes??


Are these "golden tickets" going to lead to their ultimate undoing?

Review crumbs on the board re: 'gold'.


#SEALTeam6 Trump re-tweeted this.